© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9074
    Prev
    Next
    INDEX
    Explanations

    nested structures or patterns in data, particularly focusing on indices and selections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code and math symbols

    np_acts-logits-general · gemini-2.0-flash

    colon or comma after numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )]:
    -0.70
     ویکی‌پدیا
    -0.68
    )";
    -0.65
    Демографія
    -0.65
     ]
    -0.62
     ويكيپيديا
    -0.59
     }}$}
    -0.59
    tvguidetime
    -0.59
    الدراسه
    -0.58
    SOUNDBITE
    -0.58
    POSITIVE LOGITS
    ..
    0.69
    ItemBackground
    0.65
    ..<
    0.62
    ..(
    0.58
     ..
    0.56
    ～
    0.54
    …
    0.54
     até
    0.53
    until
    0.51
     sampai
    0.49
    Activations Density 0.975%

    No Known Activations